AI钱塘论坛（第39期）
主题：Beyond Scaling: Visual Learning by Adaptation
时间：2025年11月19日 上午 9-12点
地点：10教410会议室
主持人：周晓飞
王洋博士，现任加拿大康考迪亚大学（Concordia University）计算机科学与软件工程系副教授。此前，他执教于曼尼托巴大学。2020-2022 年期间，他担任华为加拿大消费者业务部计算机视觉首席科学家（技术副总裁）。他在西蒙弗雷泽大学获得博士学位，在阿尔伯塔大学获得硕士学位，在哈尔滨工业大学获得工学学士学位。在加入曼尼托巴大学之前，他曾在伊利诺伊大学香槟分校（University of Illinois Urbana-Champaign）担任NSERC 博士后研究员。他的研究重点是计算机视觉和机器学习。
报告摘要：There have been significant advances in computer vision in the past decade. Current computer vision systems usually learn a generic model. In order to handle the diversity of the visual world, the current approach is to scale up the model. Although scaling has been proven effective in the era of large language model, I argue that there are also other alternative approaches we should explore. In this talk, I will introduce some of our recent work on building robust computer vision systems via adaptation and continual learning. Instead of learning and deploying one generic model, our goal is to learn a model that can effectively and continuously adapt itself to different environments. I will present applications of this framework in several computer vision applications.